Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1432. Min Range: -7.1432
Max Act: 7.1432. Min Act: -0.1700
Data Index: 692764 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1432. Min Range: -7.1432
Max Act: 7.0495. Min Act: -0.1700
Data Index: 8072368 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.9557. Min Act: -0.1700
Data Index: 4524395 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.8620. Min Act: -0.1700
Data Index: 6340287 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.8307. Min Act: -0.1700
Data Index: 73475 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.8620. Min Act: -0.1700
Data Index: 4949238 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7682. Min Act: -0.1700
Data Index: 4633395 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7682. Min Act: -0.1700
Data Index: 7299061 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7370. Min Act: -0.1700
Data Index: 5205966 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7370. Min Act: -0.1700
Data Index: 3684305 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7370. Min Act: -0.1700
Data Index: 7802333 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7057. Min Act: -0.1700
Data Index: 451015 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7057. Min Act: -0.1700
Data Index: 8500617 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.7057. Min Act: -0.1700
Data Index: 5304624 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.6745. Min Act: -0.1700
Data Index: 6846355 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.6432. Min Act: -0.1700
Data Index: 1861928 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.6432. Min Act: -0.1700
Data Index: 3469416 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.5807. Min Act: -0.1700
Data Index: 339072 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.6432. Min Act: -0.1700
Data Index: 4885661 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1432. Min Range: -7.1432
Max Act: 6.6120. Min Act: -0.1700
Data Index: 4544795 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19